# A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models

arXiv: https://arxiv.org/abs/2503.01854 · HTML: https://mlsanity.com/paper/2503.01854/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 42 of its 54 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 42)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Eight Methods to Evaluate Robust Unlearning in LLMs](https://mlsanity.com/paper/2402.16835/) (2024)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Continual Learning and Private Unlearning](https://mlsanity.com/paper/2203.12817/) (2022)
- [An Adversarial Perspective on Machine Unlearning for AI Safety](https://mlsanity.com/paper/2409.18025/) (2024)
- [Machine Unlearning of Pre-trained Large Language Models](https://mlsanity.com/paper/2402.15159/) (2024)
- [Large Language Model Unlearning via Embedding-Corrupted Prompts](https://mlsanity.com/paper/2406.07933/) (2024)
- [Guardrail Baselines for Unlearning in LLMs](https://mlsanity.com/paper/2403.03329/) (2024)
- [Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference](https://mlsanity.com/paper/2406.08607/) (2024)
- [Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning](https://mlsanity.com/paper/2406.13356/) (2024)
- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models](https://mlsanity.com/paper/2310.20138/) (2023)
- [RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2406.10890/) (2024)
- [Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench](https://mlsanity.com/paper/2410.22108/) (2024)
- [A Closer Look at Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2410.08109/) (2024)
- [Machine Unlearning in Generative AI: A Survey](https://mlsanity.com/paper/2407.20516/) (2024)
- [Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2405.12523/) (2024)
- [CLEAR: Character Unlearning in Textual and Visual Modalities](https://mlsanity.com/paper/2410.18057/) (2024)
- [Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization](https://mlsanity.com/paper/2410.12949/) (2024)

## Built on by (most cited first, 30 of 34)

- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Model Unlearning via Sparse Autoencoder Subspace Guided Projections](https://mlsanity.com/paper/2505.24428/) (2025)
- [LLM Unlearning with LLM Beliefs](https://mlsanity.com/paper/2510.19422/) (2025)
- [Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness](https://mlsanity.com/paper/2506.05735/) (2025)
- [SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders](https://mlsanity.com/paper/2503.14530/) (2025)
- [CRISP: Persistent Concept Unlearning via Sparse Autoencoders](https://mlsanity.com/paper/2508.13650/) (2025)
- [LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples](https://mlsanity.com/paper/2512.07375/) (2025)
- [Agentic Unlearning: When LLM Agent Meets Machine Unlearning](https://mlsanity.com/paper/2602.17692/) (2026)
- [From Weights to Activations: Is Steering the Next Frontier of Adaptation?](https://mlsanity.com/paper/2604.14090/) (2026)
- [Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks](https://mlsanity.com/paper/2607.07907/) (2026)
- [Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking](https://mlsanity.com/paper/2508.02435/) (2025)
- [UniErase: Towards Balanced and Precise Unlearning in Language Models](https://mlsanity.com/paper/2505.15674/) (2025)
- [DUSK: Do Not Unlearn Shared Knowledge](https://mlsanity.com/paper/2505.15209/) (2025)
- [Reinforcement Unlearning via Group Relative Policy Optimization](https://mlsanity.com/paper/2601.20568/) (2026)
- [LLM Unlearning Should Be Form-Independent](https://mlsanity.com/paper/2506.07795/) (2025)
- [Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2606.00105/) (2026)
- [Feature-Selective Representation Misdirection for Machine Unlearning](https://mlsanity.com/paper/2512.16297/) (2025)
- [Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs](https://mlsanity.com/paper/2609.10439/) (2026)
- [Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization](https://mlsanity.com/paper/2509.20230/) (2025)
- [Steerability of Instrumental-Convergence Tendencies in LLMs](https://mlsanity.com/paper/2601.01584/) (2026)
- [ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models](https://mlsanity.com/paper/2601.08189/) (2026)
- [Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning](https://mlsanity.com/paper/2602.19612/) (2026)
- [Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On](https://mlsanity.com/paper/2605.19035/) (2026)
- [Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning](https://mlsanity.com/paper/2607.27968/) (2026)
- [ST2U: Stateful Test-Time Unlearning via Restricted Knowledge Boundary Control](https://mlsanity.com/paper/2608.23034/) (2026)
- [Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data](https://mlsanity.com/paper/2511.19498/) (2025)
- [textbfAGTAO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality](https://mlsanity.com/paper/2602.01703/) (2026)
- [Seamless Deception: Larger Language Models Are Better Knowledge Concealers](https://mlsanity.com/paper/2603.14672/) (2026)
- [oslash Source Models Leak What They Shouldn't nrightarrow: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization](https://mlsanity.com/paper/2604.08238/) (2026)

## Abstract (arXiv)

This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as textitLLM unlearning. LLM unlearning offers a principled approach to removing the influence of undesirable data (e.g., sensitive or illegal information) from LLMs, while preserving their overall utility without requiring full retraining. Despite growing research interest, there is no comprehensive survey that systematically organizes existing work and distills key insights; here, we aim to bridge this gap. We begin by introducing the definition and the paradigms of LLM unlearning, followed by a comprehensive taxonomy of existing unlearning studies. Next, we categorize current unlearning approaches, summarizing their strengths and limitations. Additionally, we review evaluation metrics and benchmarks, providing a structured overview of current assessment methodologies. Finally, we outline promising directions for future research, highlighting key challenges and opportunities in the field.